Methodology as scientific reasoning

The essence of science, as it is understood today, lies in the scientific method. This methodological framework constitutes the cornerstone upon which scientific progress is built. Its foundation is experience. I conceive methodology as the application of reason to situations characterized by uncertainty. Within this context, statistics serves this purpose as a kind of “language” designed to address questions of genuine scientific relevance.

Uncertainty and statistical inference

Not everyone tolerates uncertainty well. There are even specific periods in a person’s life during which the presence of uncertainty is experienced as aversive, unpleasant, and even harmful. Statistics has developed a range of tools and models that help scientists manage uncertainty when making decisions. Both classical (also known as “frequentist”) statistical inference and Bayesian (also known as “subjective”) statistical inference are highly valuable for integrating scientific evidence without adopting dogmatic or polarized positions. I believe that this deliberately unbiased and prejudice-free approach is what should inspire scientific practice today.

Probabilistic and network-based modeling

Popular wisdom suggests that “the world is small”, a notion that is supported both by the mathematics of graphical models and by psychosocial research. It is relatively easy to establish contact with almost anyone in the world by relying solely on our acquaintances, precisely because humanity can be understood as a beautifully and ingeniously connected network. What has come to be known as “network science” has contributed to the understanding of a wide range of natural and artificial phenomena, making this theoretical and practical approach particularly useful for advancing our understanding of psychological phenomena. In this regard, probabilistic networks, both Bayesian and non-Bayesian, are especially relevant to psychology. I believe that these statistical and mathematical tools are key to addressing the intrinsic complexity of psychological phenomena without losing sight of their fundamentally probabilistic nature.

Models as bridges between theory and data

A model is, in essence, “a simplification of reality”. Models are not reality itself, but they are enormously useful for approaching it. They help test theories, interpret data, and make decisions that are consistent with specific utility parameters. Accordingly, a model can be understood as a tool that allows us to approach decision-making in a reasoned and justified manner, free from the constraints of routine analytical practices. I therefore regard the use of models as central to scientific practice, as they allow the intellect to go beyond what is immediately accessible through reasoning alone.

Principles of rigorous and transparent research

• Rigor
• Transparency
• Reproducibility
• Cumulative science
• Constructive critical thinking